40 datasets found

The Google-RE (Templates) dataset contains 6.11K template-based prompts from Wikipedia and 3 relations.

The dataset is an annotated corpus of pedagogical roles for the study of pedagogical value.

Quasar: Datasets for question answering by search and reading.

Open-domain question answering (OpenQA) aims to seek answers for a broad range of questions from a large knowledge source, e.g., structured knowledge bases and unstructured...

This paper proposes a novel joint training approach for dense passage retrieval and passage re-ranking.

The authors used the Jeopardy questions dataset for their experiments.

The authors used the CountryQA dataset for their experiments.

The authors used a variety of datasets for question answering, including TriviaQA, Natural Questions, CountryQA, and Jeopardy questions.

SCHOLAR is a collection of utterances querying an academic database, and GEO is a classic dataset with queries about U.S. geography.

Semantic parsers map natural language utterances into meaning representations (e.g. programs). Such models are typically bottle-necked by the paucity of training data due to the...

The paper proposes a novel approach to the sequential example selection paradigm for in-context learning.

Open-domain QA datasets for testing the proposed method

ChroniclingAmericaQA is a large-scale question-answering dataset comprising 487k question-answer pairs over a collection of historical American newspapers with the objective of...

The TruthfulQA dataset is a dataset that contains 817 questions designed to evaluate language models' preference to mimic some human falsehoods.

The BioASQ dataset contains questions and answers from various sources, including Wikipedia and biomedical literature.

The Yin-Yang dataset is a benchmark for evaluating the performance of question answering systems.

The dataset used in the paper is Natural Questions and TriviaQA, two popular datasets for open-domain question answering.

The BEIR dataset is a large-scale zero-shot evaluation dataset for information retrieval models, consisting of 13,000 documents and 1,000 questions.

The TREC Deep Learning track dataset is a collection of question answering datasets, which are used for passage retrieval and ranking.

The Quora Question Pairs (QQP) dataset consists of 50,000 question pairs labeled with paraphrase or non-paraphrase.